Remembering Conversations

# Remembering Conversations

Search archived conversations using semantic similarity or exact text matching.

**Core principle:** Search before reinventing.

**Announce:** "I'm searching previous conversations for [topic]."

**Setup:** See INDEXING.md

## When to Use

**Search when:**
- Your human partner mentions "we discussed this before"
- Debugging similar issues
- Looking for architectural decisions or patterns
- Before implementing something familiar

**Don't search when:**
- Info in current conversation
- Question about current codebase (use Grep/Read)

## In-Session Use

**Always use subagents** (50-100x context savings). See skills/getting-started for workflow.

**Manual/CLI use:** Direct search (below) for humans outside Claude Code sessions.

## Direct Search (Manual/CLI)

**Tool:** `~/.claude/skills/collaboration/remembering-conversations/tool/search-conversations`

**Modes:**
```bash
search-conversations "query"              # Vector similarity (default)
search-conversations --text "exact"       # Exact string match
search-conversations --both "query"       # Both modes
```

**Flags:**
```bash
--after YYYY-MM-DD    # Filter by date
--before YYYY-MM-DD   # Filter by date
--limit N             # Max results (default: 10)
--help                # Full usage
```

**Examples:**
```bash
# Semantic search
search-conversations "React Router authentication errors"

# Find git SHA
search-conversations --text "a1b2c3d4"

# Time range
search-conversations --after 2025-09-01 "refactoring"
```

Returns: project, date, conversation summary, matched exchange, similarity %, file path.

**For details:** Run `search-conversations --help`


# Conversation Search Deployment Guide

Quick reference for deploying and maintaining the conversation indexing system.

## Initial Deployment

```bash
cd ~/.claude/skills/collaboration/remembering-conversations/tool

# 1. Install hook
./install-hook

# 2. Index existing conversations (with parallel summarization)
./index-conversations --cleanup --concurrency 8

# 3. Verify index health
./index-conversations --verify

# 4. Test search
./search-conversations "test query"
```

**Expected results:**
- Hook installed at `~/.claude/hooks/sessionEnd`
- Summaries created for all conversations (50-120 words each)
- Search returns relevant results in <1 second
- No verification errors

**Performance tip:** Use `--concurrency 8` or `--concurrency 16` for 8-16x faster summarization on initial indexing. Hook uses concurrency=1 (safe for background).

## Ongoing Maintenance

### Automatic (No Action Required)

- Hook runs after every session ends
- New conversations indexed in background (<30 sec per conversation)
- Summaries generated automatically

### Weekly Health Check

```bash
cd ~/.claude/skills/collaboration/remembering-conversations/tool
./index-conversations --verify
```

If issues found:
```bash
./index-conversations --repair
```

### After System Changes

| Change | Action |
|--------|--------|
| Moved conversation archive | Update paths in code, run `--rebuild` |
| Updated CLAUDE.md | Run `--verify` to check for issues |
| Changed database schema | Backup DB, run `--rebuild` |
| Hook not running | Check executable: `chmod +x ~/.claude/hooks/sessionEnd` |

## Recovery Scenarios

| Issue | Diagnosis | Fix |
|-------|-----------|-----|
| **Missing summaries** | `--verify` shows "Missing summaries: N" | `--repair` regenerates missing summaries |
| **Orphaned DB entries** | `--verify` shows "Orphaned entries: N" | `--repair` removes orphaned entries |
| **Out